|
Medial Code Documentation
|
this file defines utils to group data by integer keys Input: given input sequence (key,value), (k1,v1), (k2,v2) Ouptupt: an array of values data = [v1,v2,v3 .. vn] and a group pointer ptr, data[ptr[k]:ptr[k+1]] contains values that corresponds to key k More...
#include <cstddef>#include <vector>#include <algorithm>#include <utility>#include "xgboost/base.h"Go to the source code of this file.
Data Structures | |
| class | xgboost::common::ParallelGroupBuilder< ValueType, SizeType, is_row_major > |
| multi-thread version of group builder More... | |
Namespaces | |
| namespace | xgboost |
| namespace of xgboost | |
| namespace | xgboost::common |
| Copyright 2017-2023, XGBoost Contributors. | |
this file defines utils to group data by integer keys Input: given input sequence (key,value), (k1,v1), (k2,v2) Ouptupt: an array of values data = [v1,v2,v3 .. vn] and a group pointer ptr, data[ptr[k]:ptr[k+1]] contains values that corresponds to key k
Copyright 2014-2021 by Contributors
This can be used to construct CSR/CSC matrix from un-ordered input The major algorithm is a two pass linear scan algorithm that requires two pass scan over the data